Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

added more abbreviations

This commit is contained in:
DuyguA 2018-03-09 10:13:00 +01:00 committed by 4altinok
parent cca87756d7
commit 7a780476af
1 changed files with 20 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
spacy/lang/tr/tokenizer_exceptions.py
View File

@ -11,39 +11,45 @@ _exc = {
for exc_data in [
{ORTH: "A.B.D.", NORM: "Amerika Birleşik Devletleri"},
{ORT: "Alb.", NORM: "Albay"},
{ORT: "Ar.Gör.", NORM: "Araştırma Görevlisi"},
{ORT: "Arş.Gör.", NORM: "Araştırma Görevlisi"},
{ORT: "Asb.", NORM: "Astsubay"},
{ORT: "Astsb.", NORM: "Astsubay"},
{ORT: "As.İz.", NORM: "Askeri İnzibat"},
{ORT: "Atğm", NORM: "Asteğmen"},
{ORT: "Av.", NORM: "Avukat"},
{ORT: "Apt.", NORM: "Apartmanı"},
{ORTH: "A.B.D.", NORM: "Amerika Birleşik Devletleri"},
{ORTH: "Bçvş.", NORM: "Başçavuş"},
{ORTH: "bk.", NORM: "bakınız"},
{ORTH: "bknz.", NORM: "bakınız"},
{ORTH: "Bnb.", NORM: "Binbaşı"},
{ORTH: "bnb.", NORM: "binbaşı"},
{ORTH: "Böl.", NORM: "Bölümü"},
{ORTH: "Bşk.", NORM: "Başkanlığı"},
{ORTH: "Bştbp.", NORM: "Baştabip"},
{ORTH: "Bul.", NORM: "Bulvarı"},
{ORTH: "Cad.", NORM: "Caddesi"},
{ORTH: "çev.", NORM: "çeviren"},
{ORTH: "Çvş.", NORM: "Çavuş"},
{ORTH: "dak.", NORM: "dakika"},
{ORTH: "dk.", NORM: "dakika"},
{ORTH: "Doç.", NORM: "Doçent"},
{ORTH: "doğ.", NORM: "doğum tarihi"},
{ORTH: "drl.", NORM: "derleyen"},
{ORTH: "dk.", NORM: "dakika"},
{ORTH: "Dz.", NORM: "Deniz"},
{ORTH: "Dz.K.K.lığı", NORM: "Deniz Kuvvetleri Komutanlığı"},
{ORTH: "Dz.Kuv.", NORM: "Deniz Kuvvetleri"},
{ORTH: "Dz.Kuv.K.", NORM: "Deniz Kuvvetleri Komutanlığı"},
{ORTH: "dzl.", NORM: "düzenleyen"},
{ORTH: "Ecz.", NORM: "Eczanesi"},
{ORTH: "ekon.", NORM: "ekonomi"},
{ORTH: "Fak.", NORM: "Fakültesi"},
{ORTH: "gr.", NORM: "gram"},
{ORTH: "Gn.", NORM: "Genel"},
{ORTH: "Gnkur.", NORM: "Genelkurmay"},
{ORTH: "Gn.Kur.", NORM: "Genelkurmay"},
{ORTH: "gr.", NORM: "gram"},
{ORTH: "Hst.", NORM: "Hastanesi"},
{ORTH: "Hs.Uzm.", NORM: "Hesap Uzmanı"},
{ORTH: "huk.", NORM: "hukuk"},
@ -79,9 +85,12 @@ for exc_data in [
{ORTH: "Sok.", NORM: "Sokak"},
{ORTH: "Şb.", NORM: "Şube"},
{ORTH: "Şti.", NORM: "Şirketi"},
{ORTH: "Tbp.", NORM: "Tabip"},
{ORTH: "T.C.", NORM: "Türkiye Cumhuriyeti"},
{ORTH: "Tel.", NORM: "Telefon"},
{ORTH: "tel.", NORM: "telefon"},
{ORTH: "telg.", NORM: "telgraf"},
{ORTH: "Tğm.", NORM: "Teğmen"},
{ORTH: "tğm.", NORM: "teğmen"},
{ORTH: "tic.", NORM: "ticaret"},
{ORTH: "Tug.", NORM: "Tugay"},
@ -89,11 +98,16 @@ for exc_data in [
{ORTH: "Tümg.", NORM: "Tümgeneral"},
{ORTH: "Uzm.", NORM: "Uzman"},
{ORTH: "Üçvş.", NORM: "Üstçavuş"},
{ORTH: "Üni.", NORM: "Üniversitesi"},
{ORTH: "Ütğm.", NORM: "Üsteğmen"},
{ORTH: "vb.", NORM: "ve benzeri"},
{ORTH: "vs.", NORM: "vesaire"},
{ORTH: "Yard.", NORM: "Yardımcı"},
{ORTH: "Yar.", NORM: "Yardımcı"},
{ORTH: "Yb.", NORM: "Yarbay"},
{ORTH: "Yd.Sb.", NORM: "Yedek Subay"},
{ORTH: "Yard.Doç.", NORM: "Yardımcı Doçent"},
{ORTH: "Yar.Doç.", NORM: "Yardımcı Doçent"},
{ORTH: "Yb.", NORM: "Yarbay"},
{ORTH: "Yrd.", NORM: "Yardımcı"},
{ORTH: "Yrd.Doç.", NORM: "Yardımcı Doçent"},
{ORTH: "Y.Müh.", NORM: "Yüksek mühendis"},
@ -101,7 +115,8 @@ for exc_data in [
_exc[exc_data[ORTH]] = [exc_data]
for orth in ["Dr."]:
for orth in [
"Dr.", "yy."]:
_exc[orth] = [{ORTH: orth}]